Mixed initiative serves as one of the key factors in controlling conversation directions. For a speaker, responding passively or leading proactively would result in rather different responses. However, most dialogue systems focus on training a holistic response generation model without any distinction among different initiatives. It leads to the cross-contamination problem, where the model confuses different initiatives and generates inappropriate responses. Moreover, obtaining plenty of human annotations for initiative labels can be expensive. To address this issue, we propose a general mix-Initiative Dynamic Prefix Tuning framework (IDPT) to decouple different initiatives from the generation model, which learns initiative-aware prefixes in both supervised and unsupervised settings. Specifically, IDPT decouples initiative factors into different prefix parameters and uses the attention mechanism to adjust the selection of initiatives in guiding generation dynamically. The prefix parameters can be tuned towards accurate initiative prediction as well as mix-initiative response generation. Extensive experiments on two public dialogue datasets show that the proposed IDPT outperforms previous baselines on both automatic metrics and human evaluations. It also manages to generate appropriate responses with manipulated initiatives.

翻译：混合主动性是控制对话方向的关键因素之一。对于说话者而言，被动回应与主动引导会导致截然不同的回应结果。然而，大多数对话系统仅关注训练整体性的响应生成模型，并未区分不同主动性类型。这会导致交叉污染问题——模型混淆不同主动性类型并生成不恰当的回应。此外，获取大量主动性标签的人工标注成本高昂。为解决这一问题，我们提出通用混合主动动态前缀调优框架（IDPT），该框架通过学习主动性感知前缀（涵盖监督与无监督场景）将不同主动性从生成模型中解耦。具体而言，IDPT将主动性因素解耦为不同的前缀参数，并利用注意力机制动态调整指导生成时的主动性选择。前缀参数可针对准确的主动性预测及混合主动式响应生成进行调优。在两个公开对话数据集上的大量实验表明，所提出的IDPT在自动评估指标与人工评测上均优于现有基线模型，并能有效生成受控主动性的恰当回应。